White blood cell segmentation method for color blood cell images based on superpixels and anomaly detection

Abstract

The invention discloses a white blood cell segmentation method based on super pixels and an anomaly detection color blood cell image. The method includes the steps that firstly, CMYK and HIS color space of an original color blood cell RGB image is combined with image airspace information, a seven-dimension feature vector is established, an image is pre-segmented by an SLIC superpixel partitioning algorithm, and a superpixel segmentation image is obtained; secondly, a cell nucleus area is detected by using an abnormal target detection method, an abnormal energy value image of each pixel point is obtained, and a pre-segmented cell nucleus area image is obtained after area smoothing and threshold segmentation are conducted; finally, corresponding superpixel areas of the pre-segmented cell nucleus area image and the superpixel segmentation image are combined, as for H component of white blood cell HSI space, surrounding pixel points of a cell nucleus are selected to serve as seed points to conduct area growing, the surrounding pixel points are combined with a pre-segmented superpixel image, and white blood cells are segmented out. The segmentation algorithm is simple, the segmentation speed is high, part space information is adopted during segmenting, and the segmentation is more accurate.

Description

technical field [0001] The invention belongs to the field of biomedical image processing, in particular to a white blood cell segmentation method for color blood cell images based on superpixels and abnormal detection. Background technique [0002] White blood cells are the main component of the human immune system, which can resist and eliminate invading pathogenic microorganisms. The content of white blood cells in the blood of normal people is relatively stable, about 4000-10000 / microliter, and abnormal blood cell content indicates that there may be some kind of disease in the human body. [0003] White blood cell differential count is one of the routine blood test items in the hospital. In clinical diagnosis, it is of great significance to accurately measure the content of various white blood cells in the blood. At present, the conventional white blood cell counting methods are manual counting and automatic counting. Manual counting is time-consuming and laborious, with...

AI Technical Summary

Problems solved by technology

At present, the conventional white blood cell counting methods are manual counting and automatic counting. Manual counting is time-consuming and laborious, and the accuracy is not high, which does not meet the medical rapid and accurate diagnostic standards.

[0004] Color image processing has been successfully applied to the classification and counting of white blood cells, but there are still many problems, such as the segmentation of white blood cell nuclei and cytoplasm, etc.

Images